INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تانيه

-1.12

IntentFilter

-0.69

elemField

-0.68

 Cochrane

-0.68

ंदीखरीदारी

-0.66

niczy

-0.65

 Alford

-0.64

 مرئيه

-0.63

 DriverManager

-0.63

addPreferredGap

-0.62

POSITIVE LOGITS

 Philadelphia

1.41

 Pennsylvania

1.39

Philadelphia

1.31

Pennsylvania

1.25

 Philly

1.24

 Philadel

1.23

 PHILADELPHIA

1.19

 PENNSYLVANIA

1.16

 Phila

1.10

Philly

1.06

Activations Density 0.072%

No Comments

No Known Activations